pESTO: Iterative p-greedy kernel regression with risk-driven Early STOpping
stat.ML, cs.LG
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Greedy regularized kernel interpolation
- Greedy techniques for inverse problems
- Enhancing Gaussian Process Surrogates for Optimization and Posterior Approximation via Random Exploration
- Reliable sampling-based RKHS norm estimation via superconvergence
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference